© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 116469
    Prev
    Next
    INDEX
    Explanations

    directional terms and references to right and left

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    elen
    -0.08
    obo
    -0.07
    ãĥ¼ãĥį
    -0.07
    ogne
    -0.07
    æľĹ
    -0.07
    elder
    -0.07
    embre
    -0.07
    rub
    -0.06
    oga
    -0.06
    obox
    -0.06
    POSITIVE LOGITS
    shan
    0.07
     glo
    0.07
    :&
    0.06
    Unnamed
    0.06
     regional
    0.06
     macro
    0.06
     progression
    0.06
    actable
    0.06
    -right
    0.06
     ranger
    0.06
    Activations Density 0.001%

    No Known Activations